Medical Reasoning
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
77.3Fatty Liver Assessment
13
Mar 27, 2026
79.3Accuracy
12
Apr 29, 2026
59.4Pass@1
12
Apr 15, 2026
59.7pass@1
12
Apr 15, 2026
29.68BLEU-1
12
Apr 10, 2026
61.1EM
12
Apr 10, 2026
84.05Exact Match (EM)
12
Apr 10, 2026
1Wins
12
Feb 26, 2026
0.513Wins
12
Feb 26, 2026
0.52MEDQA
12
Feb 26, 2026
77.7Accuracy
11
May 26, 2026
1,509Token Cost (tokens/question)
11
Apr 1, 2026
1,350Token Cost (tokens/question)
11
Apr 1, 2026
1,742Token Cost
11
Apr 1, 2026
1,047Token Cost (tokens/question)
11
Apr 1, 2026
2,391Token Cost (tokens/question)
11
Apr 1, 2026
2,383Token Cost
11
Apr 1, 2026
90.2Performance Score
11
Mar 31, 2026
77.3Anatomy (AN) Accuracy
10
Jun 23, 2026
22.6Accuracy
9
Jun 30, 2026
83Accuracy+
9
Jun 30, 2026
62Accuracy (Attenuation Pattern)
9
Feb 26, 2026
0.77Fatty Liver Accuracy
9
Feb 26, 2026
57.6WR vs Base
8
May 11, 2026
0.383Accuracy
8
Feb 26, 2026